# What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment

arXiv: https://arxiv.org/abs/2509.12750 · HTML: https://mlsanity.com/paper/2509.12750/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark](https://mlsanity.com/paper/2402.04788/) (2024)
- [Secrets of RLHF in Large Language Models Part II: Reward Modeling](https://mlsanity.com/paper/2401.06080/) (2024)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates](https://mlsanity.com/paper/2408.13006/) (2024)
- [AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception](https://mlsanity.com/paper/2404.09624/) (2024)
- [UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark](https://mlsanity.com/paper/2404.09619/) (2024)
- [Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content](https://mlsanity.com/paper/2503.02357/) (2025)
- [From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans](https://mlsanity.com/paper/2509.06607/) (2025)
- [MLLM-as-a-Judge for Image Safety without Human Labeling](https://mlsanity.com/paper/2501.00192/) (2024)
- [VLRM: Vision-Language Models act as Reward Models for Image Captioning](https://mlsanity.com/paper/2404.01911/) (2024)
- [Assessing Data Quality of Annotations with Krippendorff Alpha For Applications in Computer Vision](https://mlsanity.com/paper/1912.10107/) (2019)

## Built on by (most cited first, 1 of 1)

- [Order Matters: LVLMs as Judges for Temporal Reasoning in Image Sequences](https://mlsanity.com/paper/2608.10908/) (2026)

## Abstract (arXiv)

Automated evaluation of generative text-to-image models remains a challenging problem. Recent works have proposed using multimodal LLMs to judge the quality of images, but these works offer little insight into how multimodal LLMs make use of concepts relevant to humans, such as image style or composition, to generate their overall assessment. In this work, we study what attributes of an image--specifically aesthetics, lack of artifacts, anatomical accuracy, compositional correctness, object adherence, and style--are important for both LLMs and humans to make judgments on image quality. We first curate a dataset of human preferences using synthetically generated image pairs. We use inter-task correlation between each pair of image quality attributes to understand which attributes are related in making human judgments. Repeating the same analysis with LLMs, we find that the relationships between image quality attributes are much weaker. Finally, we study individual image quality attributes by generating synthetic datasets with a high degree of control for each axis. Humans are able to easily judge the quality of an image with respect to all of the specific image quality attributes (e.g. high vs. low aesthetic image), however we find that some attributes, such as anatomical accuracy, are much more difficult for multimodal LLMs to learn to judge. Taken together, these findings reveal interesting differences between how humans and multimodal LLMs perceive images.